Community detection is a fundamental problem in network analysis, with many applications in various fields. Extending community detection to the temporal setting with exact temporal accuracy, as required by real-world dynamic data, necessitates methods specifically adapted to the temporal nature of interactions. We introduce LAGO, a novel method for uncovering dynamic communities by greedy optimization of Longitudinal Modularity, a specific adaptation of Modularity for continuous-time networks. Unlike prior approaches that rely on time discretization or assume rigid community evolution, LAGO captures the precise moments when nodes enter and exit communities. We evaluate LAGO on synthetic benchmarks and real-world datasets, demonstrating its ability to efficiently uncover temporally and topologically coherent communities.

Abstract Groups—such as clusters of points or communities of nodes—are fundamental when addressing various data mining tasks. In temporal data, the predominant approach for characterizing group evolution has been through the identification of “events”. However, the events usually described in the literature, e.g., shrinks/growths, splits/merges, are often arbitrarily defined, creating a gap between such theoretical/predefined types and real-data group observations. Moving beyond existing taxonomies, we think of events as “archetypes” characterized by a unique combination of quantitative dimensions that we call “facets”. Group dynamics are defined by their position within the facet space, where archetypal events occupy extremities. Thus, rather than enforcing strict event types, our approach can allow for hybrid descriptions of dynamics involving group proximity to multiple archetypes. We apply our framework to evolving groups from several face-to-face interaction datasets, showing it enables richer, more reliable characterization of group dynamics with respect to state-of-the-art methods, especially when the groups are subject to complex relationships. Our approach also offers intuitive solutions to common tasks related to dynamic group analysis, such as choosing an appropriate aggregation scale, quantifying partition stability, and evaluating event quality.

Exceptional Model Mining (EMM) is a local pattern mining framework that generalizes subgroup discovery. In EMM, we look for subsets of objects-subgroups-whose model deviates significantly from the same model fitted on the overall dataset. Multi-objective Optimization (MOO) is an area of Multiple Criteria Decision Making where two or more functions need to be optimized at the same time and the goal is to find the best compromise between the concurrent objectives. We introduce a new model class for EMM in a MOO setting called Exceptional Pareto Front Mining. We design fitting quality measures that take into account both the distance between models and the relevance of the subgroups. We propose a beam search for top-K EMM whose added-value is studied on both synthetic and real life datasets. Among others, we discuss a use case on hyperparameter optimization in machine learning for both regression and multi-label classification.

Designing, selling and/or exploiting connected vertical urban farms is now receiving a lot of attention. In such farms, plants grow in controlled environments according to recipes that specify the different growth stages and instructions concerning many parameters (e.g., temperature, humidity, CO \(_{2}\) , light). During the whole process, automated systems collect measures of such parameters and, at the end, we can get some global indicator about the used recipe, e.g., its yield. Looking for innovative ideas to optimize recipes, we investigate the use of a new optimal subgroup discovery method from purely numerical data. It concerns here the computation of subsets of recipes whose labels (e.g., the yield) show an interesting distribution according to a quality measure. When considering optimization, e.g., maximizing the yield, our virtuous circle optimization framework iteratively improves recipes by sampling the discovered optimal subgroup description subspace. We provide our preliminary results about the added-value of this framework thanks to a plant growth simulator that enables inexpensive experiments.

Graph embedding is a technique which consists in finding a new representation for a graph usually by representing the nodes as vectors in a low-dimensional real space. In this paper, we compare some of the best known algorithms proposed over the last few years, according to four structural properties of graphs: first-order and second-order proximities, isomorphic equivalence and community membership. To study the embedding algorithms, we introduced several measures. We show that most of the algorithms are able to recover at most one of the properties and that some algorithms are more sensitive to the embedding space dimension than some others.